SSIMBaD uses a noise schedule, phi(sigma)=sigma/(sigma+0.3), chosen so that SSIM degrades linearly across diffusion steps, and reports improved anime face colorization over prior baselines.
Generative Modeling by Estimating Gradients of the Data Distribution,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.GR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SSIMBaD: Sigma Scaling with SSIM-Guided Balanced Diffusion for AnimeFace Colorization
SSIMBaD uses a noise schedule, phi(sigma)=sigma/(sigma+0.3), chosen so that SSIM degrades linearly across diffusion steps, and reports improved anime face colorization over prior baselines.